Since a computer defeated world champion Garry Kasparov in 1997, chess has been a continual marker of AI’s progress.
In December, the world marvelled at the latest machine-driven victory on the chequered board, which underlined just how far the technology has come in the last 20 years.
AlphaZero – Google Deep Mind’s gaming AI – taught itself how to play chess in under four hours with no human intervention.
Within a day it had become a master of the game. Alpha was able to process 80,000 positions per second taking what Deep Mind called a “humanlike” learning approach, if at unfathomable speed.
AI’s ability to rapidly process, learn from and objectively interpret vast amounts of data presents amazing possibilities far beyond the battle for pawns, knights and queens.
Neuro-rehab’s chessboard could be the towering piles of printed data which shape the future of patients in personal injury and negligence cases.
For each carefully planned move in pursuit of the king, read the many potential rehab interventions and outcomes informed by research and past experience.
“The use of AI in this field is inevitable. It is a question of when, not if,” says Edmund Bonikowski, whose expertise straddles neuro-rehab and AI.
The honorary consultant in neuro-rehab at Taunton and Somerset NHS Foundation Trust also produces medico-legal reports on people with brain and spinal injuries via the National Neurological Rehabilitation Chambers.
Currently, he is also investigating ways of applying AI to neuro-rehab data in medico-legal reporting, as part of a PhD programme at Cambridge University’s Information Engineering department.
“Medico-legal reports in neuro-rehab require the expert to assimilate a very wide range of inputs from a substantial body of medical records, some of which will be handwritten, with some structured and some unstructured.
“There are often other expert reports to factor in, as well as witness statements from families, friends and employers. The expert must consider all of this information, reference it against their own experience and say, ‘this is what I think’.
“For a serious personal injury or negligence case it is not uncommon to be sent a pile of paperwork that would stand two or three feet tall. On some cases I have received nine or 10 boxes of notes, or thousands of pages on an electronic file, which can be nauseating to scroll through on screen.”
While his specific focus is on revolutionising medico-legal reporting, Bonikowski believes AI could also solve neuro-rehab’s wider problematic relationship with data.
“Data in neuro-rehab is very poor and di cult to source. It is extremely hard to identify numbers of people with particular levels of disability resulting from traumatic brain injury, for example.
“Incidence and prevalence levels related to hospital admissions are available, but it is much more diffcult to get at the numbers of people with mild brain injuries who may not go to hospital, or whose injury wasn’t identified by healthcare professionals.
“Superimposed on top of that is the fact that neuro-rehab is generally poorly funded compared to other healthcare specialities. With limited resources in terms of clinical and support staff, the processing of data comes fairly low down the priority list.”
The acceleration of AI could help neuro-rehab professionals face up to such issues. And, thanks to easy-to-access networks – which are increasingly cheap, while offering higher speed and capacity – this is theoretically possible now.
“We could easily use document analysis techniques to scan through huge volumes of data and extract meaningful and related content.
“If we were giving an estimate of the risk of epilepsy occurring in a particular case, for example, it needn’t just be based on your own experience or one or two papers.
“It could be based on how many cases have been put through an algorithm and what the experience was. What were the outcomes? The data doesn’t necessarily all have to come from the personal injury or negligence world.
“It could come from other patients in the general population of brain injury sufferers. This whole process could be powered by AI.”
Whether or not AI is the definitive answer to data problems in neuro-rehab, a new and improved approach is certainly needed, says Bonikowski.
“We lack really good objective markers as so much of this field is subjective. Unlike haematology, for example, in which blood counts can be measured and plotted, we just don’t have enough of this type of information.
“Also, the field we are working in is so multidisciplinary and multifaceted. Brain injury covers physical impairment and disability, as well as cognitive and behavioural problems. An injury impacts so many areas. Representing this complex situation within poorly resourced services is virtually impossible.”
Medico-legal experts must swim through oceans of complex data in search of relevant and valuable insights.
Ultimately they are charged with delivering professionally correct advice, while giving the court three vital elements: brevity, clarity and reasoning. The challenge is intensified by an ongoing influx of additional data which must be factored into each case.
“New information comes into the process, perhaps related to the deterioration of the client, the impact of new interventions or perspectives previously unseen.
“The expert must incorporate these into their evolving viewpoint. Views must also be based on research evidence. Because medical science is very fast-moving, it’s not always easy to keep up with the very latest developments.
“Furthermore, research evidence is often viewed differently from one expert to the next, causing further difficulties.”
The adversarial nature of personal injury and negligence cases can also cloud the process.
“Our opinion is for a lay judge to assimilate a complicated medical process. The difficulty for the judge is when they see two opinions and have no way of knowing which one is right.
“Through AI, there is an objectification of the opinion – views become much more objective than subjective.
“This is a fundamental principle of AI; to be able to arbitrate between views and say, with a degree of certainty, what’s right and what’s wrong.”
AI also has the potential to challenge the lack of consistency which inevitably arises in tasks carried out exclusively by humans, says Bonikowski.
“AI is simply a way of incorporating human experience into mathematical machines or algorithms.”
An algorithm is a process or set of rules to be followed in calculations or other problem-solving operations.
The more information processed by an algorithm, or system driven by algorithms, the more reliable its results.
“If thousands of brain injury cases were put through an algorithm, then the certainty of the outcome, and consistency, increases.
“In contrast, a human expert may recollect their experiences differently tomorrow from how they did today, if their mind is distracted.”
Crucially AI is able to analyse data spanning a far greater number of dimensions than is humanly possible.
While humans may be able to comprehend data on three or four dimensions, AI can make sense of it on thousands, within seconds.
It is therefore possible to find correlations between seemingly unrelated factors which may be relevant to the patient’s case.
Despite such possibilities, neuro- rehab has been slow to take advantage of AI, especially compared to more commercially minded fields.
The modern concept of AI dates back to Alan Turing’s days at Bletchley Park. Its acceleration in recent years is the result of a perfect storm of factors.
Computing capacity that can perform billions of iterations in the blink of an eye, the emergence of quality data on a massive scale and surging levels of investment are all contributing to its rapid development.
Research, administration and data- heavy tasks like due diligence are among a range of legal sector duties being influenced by AI.
In life sciences, Google is pioneering AI on several fronts. It recently launched Deep Variant, an open source tool which uses AI to draw a picture of a person’s genetic blueprint.
In 2016, it teamed up with Moorfields Eye Hospital to test whether “machine learning” technology applied to eye scan data can speed detection and treatment of eye diseases.
Machine learning is also being used extensively in the insurance industry to enable operators to better understand risk, claims and customer experience.
In financial services, fintech products and so-called ‘robo-advice’ services are increasingly fuelled by AI.
The UK government is also on board the AI bandwagon. Last year it announced plans to build a new data ethics and innovation centre aimed at ensuring ethical innovations in AI and data-based technologies.
The government is also spending £75m on progressing recommendations made in a recent independent review on AI.
Professions already embracing AI initially did so tentatively, as trust in the technology built up. This will be mirrored in neuro-rehab when the field finally catches up, says Bonikowski.
“We implicitly trust people and their opinions. If you put an expert on a personal injury case in court, there is an immense amount of trust invested in them by the patient’s family, the court and society.
“It is this degree of trust which AI machines would need to build up in order to become a fundamental source of support to expert opinion.”
With other areas of healthcare now waking up to the power of AI, neuro-rehab’s widespread adoption of the technology looks to be close.
“I would project that five years from now it will be commonplace for AI systems to be forming a fundamental platform for expert analysis and opinion; with human experts essentially validating what the AI is saying on the basis of interaction with the client and their environment.
“The analysis of all the historical and concurrent data coming in could easily be done by machine in five years.
“It could produce an analysis which states, ‘on the basis of everything here, this is the extent of the injury sustained, here is a sense of the impairment and all the other disruptions that have occurred in terms of quality of life and here are the interventions that have and haven’t been effective’.
“It could then show how an ideal healthcare system would handle the individual and the outcomes one could expect.
“All of that could come into fruition within a five-year horizon.”
An artificially intelligent army is not plotting an imminent invasion of neuro-rehab, however. Bonikowski sees AI’s presence as remaining complementary to – rather than threatening – professional roles in the sector.
“We are seeing tedious and grinding processes being replaced by machines, because they are much better at them than we are.
“The subtler, softer and empathetic human elements almost certainly will never be replaced.
“The idea that machines would be able to interface with somebody with a multifaceted, severe set of disabilities is extraordinarily far-fetched.
“But within five years we should have a really solid expert support system available, with an expert still required to validate findings and add some of the subtleties which may not come out of machine analysis.
“Often in medico-legal reporting we are asked to give a view on what the patient requires to improve functioning. I think that will always require some human interface.
“If you look in someone’s eyes and tell them they are going to need a piece of surgery or a very long period of rehab, they are much more likely to engage with a human demonstrating genuine empathy than a machine which simply says ‘from the analysis, this is what you require’.
Revolutionary neurorehab app begins national roll-out
A tech platform credited with revolutionising rehabilitation for the neuro sector goes live today as the first step in its national roll-out.
Neuro ProActive has been created to enable a fully multi-disciplinary approach to rehabilitation, covering both inpatient and community care and involving patients and their families in the process.
The app – which supports the spectrum of neurological conditions, from brain injury to stroke, dementia and Long COVID – enables greater cohesion between therapists through its end-to-end message and video calling encryption, which allows remote services and patient monitoring to be done via one single platform.
Neuro ProActive – the successor to the award-winning Stroke Active – has been in development for more than three years and goes live at UCLH Queen Square today. It will be used in its Upper Limb Neurorehabilitation Programme.
The app is set to launch into six NHS Trusts initially, with national and international expansion planned in the near future.
Professor Nick Ward, clinical lead on the Upper Limb Programme, has been a key advisor to Ian Pearce on the development of both Stroke Active and Neuro ProActive.
Ian, whose father had a stroke in 2017, was inspired to develop a platform to increase co-ordination in care to help families like his.
Whilst having no background in healthcare or tech development, Ian created Stroke Active – which was named Innovation of the Year Award at the 2019 European Neuro Convention, in recognition of the role it played in revolutionising communication between stroke professionals and promoting patient self-management – and has since created Neuro ProActive.
Working with healthcare software developers L2S2, Neuro ProActive has been created as an entirely separate platform which has been built from scratch to be entirely fit for purpose for the whole neuro sector.
“After three years of consultations with patients, families and AHPs, it’s great to see Neuro ProActive deployed at UCLH,” says Ian.
“Nick and his team were involved in the platform’s development from an early stage. The feedback we’re now getting from therapy teams all over the UK is extremely positive.
“The pandemic has severely curtailed the provision of rehab services and Neuro ProActive helps NHS Trusts adhere to NICE guidelines on patient care in a post-COVID world.”
Speaking to NR Times about its role in neuro care, Ian says: “Frequently, there is a gap between inpatient and outpatient – early supported discharge too often is just early discharge, you hear stories of people waiting six weeks before their therapy starts, which makes things so much more difficult further down the line.
“But by using the platform, we have enabled patients to connect with their community rehab team. We work across all six disciplines – neurophysio, speech and language therapy, occupational therapy, diet, arts and neuropsychology – and the whole MDT can contribute to the dashboard in real time.
“Enabling patients to have the ability to self-manage, while also including family members in the rehabilitation process, is so important. Through using the app, everyone can be involved in the process. Each patient has their own message board too, so can instantly get in touch with their team.”
How the C-Brace is opening up a new world of possibilities
The C-Brace is big news in the progression of Orthotic treatment for neurological conditions. The integration of microprocessor technology into a carbon fibre Knee Ankle Foot Orthosis (KAFO’s) opens up a whole new world of possibilities and mobility for patients dependent on full leg support to stand and walk.
As standard, KAFO users are supplied with locked knee KAFOs. This is where the knee is locked in a straight position throughout their gait cycle, but manually unlocked to allow the user to sit down with their knee flexed. The use of a locked KAFO brings about stability of the knee for users with reduced lower leg muscles strength, when walking on level ground.
However, it also results in the development of multiple gait compensations for the user to progress through the gait cycle with a locked knee. Compensations include; hip hitching on the contralateral side, circumduction during swing phase, and vaulting of the contralateral ankle.
Gait can therefore be slower, require more metabolic energy and increase mechanical stress on the sound leg. Walking on slopes and stairs with a locked knee joint is very difficult and often situations avoided by KAFO users.
An alternative option to the locked KAFO is a Stance Control Orthosis (SCO). In a similar way to the locked KAFO, the knee joint is locked straight during stance phase, but unlocks at terminal stance to allow the knee to flex through swing phase, providing a more natural gait pattern and reduction in compensatory motions to achieve ground clearance.
SCOs require considerable confidence from the user, a consistent step length and are again limited on slopes, stairs and uneven ground. In order to prevent accidental disengagement of the knee lock on challenging surfaces, the user often manually locks the SCO.
Where the C-Brace comes into its own is the significant control available in both stance and swing phase of gait. The system provides stability for the foot and ankle, and stabilises the knee in the sagittal plane with the hydraulic unit replicating the eccentric and isometric muscle contraction of the quadriceps and hamstrings.
It controls both the stance and swing phases of gait with microprocessor sensor technology that can adapt to everyday situations in real time. The technology normalises gait by allowing controlled knee flexion during weight bearing, giving patients the ability to safely navigate quick stops, walk on uneven terrain, and descend slopes, curbs and stairs step over step.
The C-Brace calculates the orientation and movement of the system in space in three dimensions, using this information to control the flexion and extension valves of a hydraulic unit that provide varying levels of resistance to knee flexion. In turn, this allows for physiological knee flexion during loading response, absorbing the shock of weight transfer during heel strike.
In a locked KAFO or SCO, that shock is directly transferred to the pelvis and lumbar spine. Additionally, the C-Brace provides microprocessor swing control that adapts to the varying walking speeds of the patient. It does not require consistent step lengths to function as SCOs do.
Variable step length means a patient can increase or decrease walking speed and length of steps based on the instantaneous activity/mobility needs, making walking safer in unfamiliar or dangerous scenarios like crossing roads.
The C-Brace is also able to provide assistance descending stairs and slopes, allowing step-over-step gait, mimicking the contraction of the quadriceps for lowering the body down a stair or slope. The C-Brace considerably reduces stress to the sound limb in unilateral users, and allows bilateral users to descend stairs and slopes and ambulate on uneven terrain.
Additional features of the C-Brace include:
Stumble recovery: The microprocessor swing control of the C-Brace provides a stumble recovery feature that activates high knee flexion resistance during swing phase extension, in preparation for stance phase, allowing the patient to fully load their orthosis and stabilise the body in case of a stumble.
Intuitive Stance Function: This feature allows the patient to stand in a safe and relaxed manner with a flexed knee without the threat of knee collapse, and automatically switches back in to ambulation mode, turning off the blocked knee flexion when the patient moves. This feature allows the patient to unload the sound leg and rest while securely standing on level or non-level surfaces.
Sitting/Kneeling Function: The C-Brace assists the patient when sitting down and standing up from a chair by providing resistance to flexion or extension.
This adds an extra degree of safety and reduces stress to the upper extremities and the sound limb. The microprocessor automatically detects when the patient begins to sit down, adjusting the hydraulic resistance against bending during the transition to sitting.
Allowing the patient to sit in a controlled manner and at a controlled rate. When standing up from a seated position, the C-Brace blocks knee flexion as soon as the knee reaches a flexion angle of 45° or less, allowing the patient to reposition the foot and load the orthosis, for improved leverage to stand. The kneeling down function allows the patient to kneel down safely with controlled flexion of the knee joint, supported by increased flexion resistance.
Activity specific modes/Freeze mode: The C-Brace is programmable for activity specific needs of the patient in addition to ambulation. For instance, resistance can be reduced to a minimum for cycling, or a flexed knee joint position can be fixed for activities such as Yoga. The user, on their personal C-brace App, can control these modes.
So how can you know if the C-Brace might be right for your patient? The first stage is a thorough assessment, considering both the indications and contraindications of the system.
- Flaccid Paralysis or partial paresis of the lower limb
- Quadriceps deficiency leading to poor knee control during stance phase
The patient may present with regular ‘giving way’ of the knee, reporting stumbles or falls when walking on flat, graduated or uneven surfaces. The C-Brace may be appropriate for a number of neurological conditions, including but not limited to:
- Spinal cord injury between L1 and L5
- Multiple sclerosis
- Neuromuscular disease
- Muscular atrophy or Traumatic paresis
Essential requirements for the use of the C-Brace:
- The user must be able to stabilise their trunk and stand without support.
- The muscles strength of the hip extensors and flexors must allow the controlled swing of the affected leg, or this must be possible through compensatory hip/trunk movement.
Contraindications of the C-Brace:
- Swing phase initiation is not possible
- Insufficient trunk stability
- Severe spasticity
- Knee or hip flexion contracture of more than 10°
- Non correctable genu varus/valgus greater than 10°
- Body weight less than 40Kg or greater than 125Kg
- Height <140cm
- Leg length discrepancy >15cm
- Fluctuating Oedema or severe skin irritation that precludes the use of an orthosis
The C-Brace Dynamic Test Orthosis (DTO) is a trial orthosis, which features the C-Brace joint unit. The DTO can be set up to each individual user and programmed to their individual gait requirements, allowing users to test the function of the orthosis within the clinical setting.
The DTO can also provide valuable evidence to the function and benefits of the C-Brace for payers. The DTO can be trialled with support from the Ottobock Orthotic Academy Clinician or through Ottobock’s clinical partner Dorset Orthopaedic.
Recruiter supports medtech business growth
A startup recruitment business is supporting the development of life-changing inventions in the neuro sector by sourcing the high-level talent to drive their ventures forward.
Hanison Green has established a niche as the only recruiter dedicated to neuromodulation and in its first eight months of trading has already helped globally-significant, early-stage businesses including ONWARD, the Swiss-based venture which hopes to launch devices within the next four years to enable paralysed people to regain the ability to move and walk.
With a specialism in supporting startups within neuromodulation, Hanison Green is working globally from its London base, with a primary focus of supporting companies in the US and Europe.
Founded by Lindsay Hartland, formerly a partner in global recruitment business SThree with over 18 years’ experience of permanent STEM leadership recruiting, he decided to form Hanison Green during the pandemic with a mission to ‘do recruitment differently’.
And the business is quickly building its reputation in neuromodulation through bringing in key new figures to leadership teams at strategically important times, maximising their chances of long-term success.
For Lindsay, while establishing a business in a new and unknown sector mid-pandemic was admittedly a risk, it’s one he was eager to take.
“If you’d have asked me eight months ago what neuromodulation was, I would have looked at you blankly, I didn’t know – but I’m a fast learner and we are already very well-connected in this exciting space of medtech” he says.
“I’ve always been really into tech and I’ve recruited in the STEM field for years, and medtech is seeing such huge and rapid development.
“It’s an area which has so much meaning to so many people. I’ve never worked in an industry space where people care so much about the end result, and I find this hugely inspiring.
“My dad had a car crash many years ago, and while he has recovered, he has constant back problems – I’ve found out that neuromodulation could be a treatment that could help.
“This technology can be genuinely life-changing, and it’s still so new that we’re only now starting to understand the possibilities. The potential is limitless.”
In addition to its specialism, Hanison Green’s approach is one that also makes it stand out from the crowd. Keen not to be regarded as a ‘typical recruiter’, its proactive approach is seeing them solve the recruitment problems businesses face, often before they have realised it themselves.
“We have a very pinpointed approach, we aim to be incredibly relevant to the company we approach and are very strategic,” says Lindsay.
“When I approached ONWARD, I had already researched their work and saw they were several years away from commercialisation, and also noticed they didn’t have a strategic commercial leader in place as yet. Anticipating that this was something likely to be under consideration, I approached them with someone I knew could help them prepare for market.
“It’s normal for CEOs to wear many hats within the business they are leading, particularly within a startup environment, but that takes them away from what that should be doing.
“We realise that and through our strategic approach, we can anticipate a leader they will be needing to guide them through their next stages of growth, and we provide that talent proactively.”
Lindsay’s highly strategic approach also extends to sourcing the candidates for these businesses.
“Generally, the talent we find is headhunted – very, very rarely are they on jobs boards, or engaged with other recruiters. Our goal is to work with the best talent, irrespective of whether they are actively on the market or not,” he says.
“I’ll tend to look for someone who has been with the same company for around four to eight years, with several promotions achieved during this time. It shows loyalty, that they’re serious about their career and are good at what they do. For me, this profile already tells me they are likely a great candidate.
“Recruitment is often seen as a numbers game, and admittedly doesn’t have a great reputation. It’s seen as an area where the recruiter throws hundreds of CVs out there in the hope something sticks, where candidates are farmed out all over the marketplace – but we want to be known for our relevance, and for the calibre of the talent we represent.”
A new and dynamic business, Hanison Green was set up during the pandemic at a time when Lindsay had the opportunity to think about the future for his family, and to see where the journey of setting up his own business would take him.
And for Lindsay, he’s happy to let that journey continue, and be guided by the opportunities and the marketplace.
“I’ve come from a corporate world where it’s all about business planning, growth, profit, all kinds of stuff like that. Everything is mapped out and fixed, and everything has to get signed-off – but I’m now really excited about the unknown,” he says.
“We’re occupying a great space in the market and will continue to build that further. We will not deviate from neuromodulation but beyond that, I don’t really have a plan for the future.
“I’m back to frontline, hands-on recruitment, which I had been out of for some years through being a partner, and I think in my older age too and having kids, I felt the need to become a role model to them, and to put my experience to better use.
“To work in something as big as this, where the end result is saving and improving the quality of people’s lives, is very meaningful indeed.”
Interviews8 months ago
The neuropsychologist teaching tai chi
Legal10 months ago
Assessments in the virtual world
News11 months ago
Meet the Moodmemo…
More headlines12 months ago
Top tech and devices for at-home stroke rehab
News8 months ago
A game-changer in rehab exercise
News10 months ago
“Because rehab won’t wait”
More headlines8 months ago
Brain injury case study: Simon’s story
News12 months ago
Leading the remote resistance